{"id":"https://openalex.org/W3127064459","doi":"https://doi.org/10.5244/c.34.89","title":"Learning To Pay Attention To Mistakes","display_name":"Learning To Pay Attention To Mistakes","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3127064459","doi":"https://doi.org/10.5244/c.34.89","mag":"3127064459"},"language":"en","primary_location":{"id":"doi:10.5244/c.34.89","doi":"https://doi.org/10.5244/c.34.89","is_oa":false,"landing_page_url":"https://doi.org/10.5244/c.34.89","pdf_url":null,"source":{"id":"https://openalex.org/S7407088578","display_name":"British Machine Vision Conference (BMVC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the British Machine Vision Conference 2020","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.15131","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073094674","display_name":"Moucheng Xu","orcid":"https://orcid.org/0000-0003-3368-9871","observed_orcids":["https://orcid.org/0000-0003-3368-9871"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Moucheng Xu","raw_affiliation_strings":["University College London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London, London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075265609","display_name":"Neil P. Oxtoby","orcid":"https://orcid.org/0000-0003-0203-3909","observed_orcids":["https://orcid.org/0000-0003-0203-3909"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Neil Oxtoby","raw_affiliation_strings":["University College London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London, London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033449704","display_name":"Daniel C. Alexander","orcid":"https://orcid.org/0000-0003-2439-350X","observed_orcids":["https://orcid.org/0000-0003-2439-350X"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel Alexander","raw_affiliation_strings":["University College London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London, London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009829456","display_name":"Joseph Jacob","orcid":"https://orcid.org/0000-0002-8054-2293","observed_orcids":["https://orcid.org/0000-0002-8054-2293"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joseph Jacob","raw_affiliation_strings":["University College London, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London, London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":0.2311,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.58177587,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9624000191688538,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9624000191688538,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.019600000232458115,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.004900000058114529,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.9539999961853027},{"id":"https://openalex.org/keywords/medical-image-segmentation","display_name":"medical image segmentation","score":0.8579999804496765},{"id":"https://openalex.org/keywords/false-negative-reduction","display_name":"false negative reduction","score":0.6650000214576721},{"id":"https://openalex.org/keywords/effective-receptive-field","display_name":"effective receptive field","score":0.675000011920929},{"id":"https://openalex.org/keywords/stroke-lesion-segmentation","display_name":"stroke lesion segmentation","score":0.7770000100135803},{"id":"https://openalex.org/keywords/vehicle-segmentation","display_name":"vehicle segmentation","score":0.5690000057220459},{"id":"https://openalex.org/keywords/magnetic-resonance-imaging","display_name":"magnetic resonance imaging","score":0.3230000138282776},{"id":"https://openalex.org/keywords/ultrasound","display_name":"ultrasound","score":0.7609999775886536},{"id":"https://openalex.org/keywords/false-positive-detection","display_name":"false positive detection","score":0.3659999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7100193500518799},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.6795068979263306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6350723505020142},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6305447220802307},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5072583556175232},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5002260208129883},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47475340962409973},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.44073486328125},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.4281367361545563},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.42208725214004517},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.41401106119155884},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4134272038936615},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.266759991645813},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.5244/c.34.89","doi":"https://doi.org/10.5244/c.34.89","is_oa":false,"landing_page_url":"https://doi.org/10.5244/c.34.89","pdf_url":null,"source":{"id":"https://openalex.org/S7407088578","display_name":"British Machine Vision Conference (BMVC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the British Machine Vision Conference 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2007.15131","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.15131","pdf_url":"https://arxiv.org/pdf/2007.15131","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10109237","doi":null,"is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10109237/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: (Proceedings) The 31st British Machine Vision Virtual Conference. (2020)","raw_type":"Proceedings paper"},{"id":"doi:10.48550/arxiv.2007.15131","doi":"https://doi.org/10.48550/arxiv.2007.15131","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.15131","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.15131","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.15131","pdf_url":"https://arxiv.org/pdf/2007.15131","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.5683000087738037}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1641498739","https://openalex.org/W1901129140","https://openalex.org/W2340897893","https://openalex.org/W2412782625","https://openalex.org/W2502312327","https://openalex.org/W2798122215","https://openalex.org/W2884555738","https://openalex.org/W2888358068","https://openalex.org/W2892466314","https://openalex.org/W2898522275","https://openalex.org/W2920218276","https://openalex.org/W2953122916","https://openalex.org/W2962961439","https://openalex.org/W2963300546","https://openalex.org/W2963794428","https://openalex.org/W2982220924"],"related_works":["https://openalex.org/W4376612726","https://openalex.org/W2913469080","https://openalex.org/W4365505210","https://openalex.org/W4221039706","https://openalex.org/W3201910501","https://openalex.org/W4408120978","https://openalex.org/W4413717288","https://openalex.org/W7134191325","https://openalex.org/W4400230716","https://openalex.org/W4231431188"],"abstract_inverted_index":{"In":[0,38],"convolutional":[1],"neural":[2],"network":[3],"based":[4],"medical":[5,168,243],"image":[6],"segmentation,":[7],"the":[8,23,64,72,89,100,118,135,180,188,203,206,213,216,225],"periphery":[9],"of":[10,26,88,179,209,215,242,252],"foreground":[11,101],"regions":[12],"representing":[13],"malignant":[14],"tissues":[15,28],"may":[16],"be":[17],"disproportionately":[18],"assigned":[19],"as":[20],"belonging":[21],"to":[22,32,47,58,91,93,111],"background":[24,119,136],"class":[25],"healthy":[27],"\\cite{attenUnet}\\cite{AttenUnet2018}\\cite{InterSeg}\\cite{UnetFrontNeuro}\\cite{LearnActiveContour}.":[29],"This":[30],"leads":[31],"high":[33,51],"false":[34,52,67,76,107],"negative":[35,53],"detection":[36],"rates.":[37],"this":[39],"paper,":[40],"we":[41],"propose":[42],"a":[43,94,112,239],"novel":[44],"attention":[45,61,165,235],"mechanism":[46,62,80,211,236],"directly":[48],"address":[49],"such":[50],"rates,":[54],"called":[55],"Paying":[56],"Attention":[57],"Mistakes.":[59],"Our":[60],"steers":[63],"models":[65,185,190],"towards":[66,75,106],"positive":[68],"identification,":[69],"which":[70,248],"counters":[71],"existing":[73],"bias":[74],"negatives.":[77],"The":[78],"proposed":[79,234],"has":[81],"two":[82],"complementary":[83],"implementations:":[84],"(a)":[85],"\"explicit\"":[86,207],"steering":[87,105],"model":[90],"attend":[92],"larger":[95],"Effective":[96,114],"Receptive":[97,115],"Field":[98,116],"on":[99,117,125],"areas;":[102],"(b)":[103],"\"implicit\"":[104],"positives,":[108],"by":[109,219,227],"attending":[110],"smaller":[113],"areas.":[120],"We":[121,159,231],"validated":[122],"our":[123,161,184,210,233],"methods":[124,162],"three":[126,181],"tasks:":[127],"1)":[128],"binary":[129],"dense":[130],"prediction":[131],"between":[132],"vehicles":[133],"and":[134,173,244],"using":[137,154],"CityScapes;":[138],"2)":[139],"Enhanced":[140],"Tumour":[141],"Core":[142],"segmentation":[143],"with":[144,163],"multi-modal":[145],"MRI":[146],"scans":[147],"in":[148,157,167,191,202],"BRATS2018;":[149],"3)":[150],"segmenting":[151],"stroke":[152],"lesions":[153],"ultrasound":[155],"images":[156],"ISLES2018.":[158],"compared":[160],"state-of-the-art":[164],"mechanisms":[166],"imaging,":[169],"including":[170],"self-attention,":[171],"spatial-attention":[172],"spatial-channel":[174],"mixed":[175],"attention.":[176],"Across":[177],"all":[178],"different":[182],"tasks,":[183,247],"consistently":[186],"outperform":[187],"baseline":[189,218],"Intersection":[192],"over":[193],"Union":[194],"(IoU)":[195],"and/or":[196],"Hausdorff":[197],"Distance":[198],"(HD).":[199],"For":[200],"instance,":[201],"second":[204],"task,":[205],"implementation":[208],"reduces":[212],"HD":[214],"best":[217],"more":[220,228],"than":[221,229],"$26\\%$,":[222],"whilst":[223],"improving":[224],"IoU":[226],"$3\\%$.":[230],"believe":[232],"can":[237],"benefit":[238],"wide":[240],"range":[241],"computer":[245],"vision":[246],"suffer":[249],"from":[250],"over-detection":[251],"background.":[253]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2021-02-15T00:00:00"}